summaryrefslogtreecommitdiffstats
path: root/fs/ext3/balloc.c
blob: baac1b129fba9642dcf5eed242a5b6f82a8b2128 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
/*
 *  linux/fs/ext3/balloc.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  Enhanced block allocation by Stephen Tweedie (sct@redhat.com), 1993
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 */

#include <linux/quotaops.h>
#include <linux/blkdev.h>
#include "ext3.h"

/*
 * balloc.c contains the blocks allocation and deallocation routines
 */

/*
 * The free blocks are managed by bitmaps.  A file system contains several
 * blocks groups.  Each group contains 1 bitmap block for blocks, 1 bitmap
 * block for inodes, N blocks for the inode table and data blocks.
 *
 * The file system contains group descriptors which are located after the
 * super block.  Each descriptor contains the number of the bitmap block and
 * the free blocks count in the block.  The descriptors are loaded in memory
 * when a file system is mounted (see ext3_fill_super).
 */


#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

/*
 * Calculate the block group number and offset, given a block number
 */
static void ext3_get_group_no_and_offset(struct super_block *sb,
	ext3_fsblk_t blocknr, unsigned long *blockgrpp, ext3_grpblk_t *offsetp)
{
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;

	blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
	if (offsetp)
		*offsetp = blocknr % EXT3_BLOCKS_PER_GROUP(sb);
	if (blockgrpp)
		*blockgrpp = blocknr / EXT3_BLOCKS_PER_GROUP(sb);
}

/**
 * ext3_get_group_desc() -- load group descriptor from disk
 * @sb:			super block
 * @block_group:	given block group
 * @bh:			pointer to the buffer head to store the block
 *			group descriptor
 */
struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb,
					     unsigned int block_group,
					     struct buffer_head ** bh)
{
	unsigned long group_desc;
	unsigned long offset;
	struct ext3_group_desc * desc;
	struct ext3_sb_info *sbi = EXT3_SB(sb);

	if (block_group >= sbi->s_groups_count) {
		ext3_error (sb, "ext3_get_group_desc",
			    "block_group >= groups_count - "
			    "block_group = %d, groups_count = %lu",
			    block_group, sbi->s_groups_count);

		return NULL;
	}
	smp_rmb();

	group_desc = block_group >> EXT3_DESC_PER_BLOCK_BITS(sb);
	offset = block_group & (EXT3_DESC_PER_BLOCK(sb) - 1);
	if (!sbi->s_group_desc[group_desc]) {
		ext3_error (sb, "ext3_get_group_desc",
			    "Group descriptor not loaded - "
			    "block_group = %d, group_desc = %lu, desc = %lu",
			     block_group, group_desc, offset);
		return NULL;
	}

	desc = (struct ext3_group_desc *) sbi->s_group_desc[group_desc]->b_data;
	if (bh)
		*bh = sbi->s_group_desc[group_desc];
	return desc + offset;
}

static int ext3_valid_block_bitmap(struct super_block *sb,
					struct ext3_group_desc *desc,
					unsigned int block_group,
					struct buffer_head *bh)
{
	ext3_grpblk_t offset;
	ext3_grpblk_t next_zero_bit;
	ext3_fsblk_t bitmap_blk;
	ext3_fsblk_t group_first_block;

	group_first_block = ext3_group_first_block_no(sb, block_group);

	/* check whether block bitmap block number is set */
	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
	offset = bitmap_blk - group_first_block;
	if (!ext3_test_bit(offset, bh->b_data))
		/* bad block bitmap */
		goto err_out;

	/* check whether the inode bitmap block number is set */
	bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
	offset = bitmap_blk - group_first_block;
	if (!ext3_test_bit(offset, bh->b_data))
		/* bad block bitmap */
		goto err_out;

	/* check whether the inode table block number is set */
	bitmap_blk = le32_to_cpu(desc->bg_inode_table);
	offset = bitmap_blk - group_first_block;
	next_zero_bit = ext3_find_next_zero_bit(bh->b_data,
				offset + EXT3_SB(sb)->s_itb_per_group,
				offset);
	if (next_zero_bit >= offset + EXT3_SB(sb)->s_itb_per_group)
		/* good bitmap for inode tables */
		return 1;

err_out:
	ext3_error(sb, __func__,
			"Invalid block bitmap - "
			"block_group = %d, block = %lu",
			block_group, bitmap_blk);
	return 0;
}

/**
 * read_block_bitmap()
 * @sb:			super block
 * @block_group:	given block group
 *
 * Read the bitmap for a given block_group,and validate the
 * bits for block/inode/inode tables are set in the bitmaps
 *
 * Return buffer_head on success or NULL in case of failure.
 */
static struct buffer_head *
read_block_bitmap(struct super_block *sb, unsigned int block_group)
{
	struct ext3_group_desc * desc;
	struct buffer_head * bh = NULL;
	ext3_fsblk_t bitmap_blk;

	desc = ext3_get_group_desc(sb, block_group, NULL);
	if (!desc)
		return NULL;
	trace_ext3_read_block_bitmap(sb, block_group);
	bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
	bh = sb_getblk(sb, bitmap_blk);
	if (unlikely(!bh)) {
		ext3_error(sb, __func__,
			    "Cannot read block bitmap - "
			    "block_group = %d, block_bitmap = %u",
			    block_group, le32_to_cpu(desc->bg_block_bitmap));
		return NULL;
	}
	if (likely(bh_uptodate_or_lock(bh)))
		return bh;

	if (bh_submit_read(bh) < 0) {
		brelse(bh);
		ext3_error(sb, __func__,
			    "Cannot read block bitmap - "
			    "block_group = %d, block_bitmap = %u",
			    block_group, le32_to_cpu(desc->bg_block_bitmap));
		return NULL;
	}
	ext3_valid_block_bitmap(sb, desc, block_group, bh);
	/*
	 * file system mounted not to panic on error, continue with corrupt
	 * bitmap
	 */
	return bh;
}
/*
 * The reservation window structure operations
 * --------------------------------------------
 * Operations include:
 * dump, find, add, remove, is_empty, find_next_reservable_window, etc.
 *
 * We use a red-black tree to represent per-filesystem reservation
 * windows.
 *
 */

/**
 * __rsv_window_dump() -- Dump the filesystem block allocation reservation map
 * @rb_root:		root of per-filesystem reservation rb tree
 * @verbose:		verbose mode
 * @fn:			function which wishes to dump the reservation map
 *
 * If verbose is turned on, it will print the whole block reservation
 * windows(start, end).	Otherwise, it will only print out the "bad" windows,
 * those windows that overlap with their immediate neighbors.
 */
#if 1
static void __rsv_window_dump(struct rb_root *root, int verbose,
			      const char *fn)
{
	struct rb_node *n;
	struct ext3_reserve_window_node *rsv, *prev;
	int bad;

restart:
	n = rb_first(root);
	bad = 0;
	prev = NULL;

	printk("Block Allocation Reservation Windows Map (%s):\n", fn);
	while (n) {
		rsv = rb_entry(n, struct ext3_reserve_window_node, rsv_node);
		if (verbose)
			printk("reservation window 0x%p "
			       "start:  %lu, end:  %lu\n",
			       rsv, rsv->rsv_start, rsv->rsv_end);
		if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
			printk("Bad reservation %p (start >= end)\n",
			       rsv);
			bad = 1;
		}
		if (prev && prev->rsv_end >= rsv->rsv_start) {
			printk("Bad reservation %p (prev->end >= start)\n",
			       rsv);
			bad = 1;
		}
		if (bad) {
			if (!verbose) {
				printk("Restarting reservation walk in verbose mode\n");
				verbose = 1;
				goto restart;
			}
		}
		n = rb_next(n);
		prev = rsv;
	}
	printk("Window map complete.\n");
	BUG_ON(bad);
}
#define rsv_window_dump(root, verbose) \
	__rsv_window_dump((root), (verbose), __func__)
#else
#define rsv_window_dump(root, verbose) do {} while (0)
#endif

/**
 * goal_in_my_reservation()
 * @rsv:		inode's reservation window
 * @grp_goal:		given goal block relative to the allocation block group
 * @group:		the current allocation block group
 * @sb:			filesystem super block
 *
 * Test if the given goal block (group relative) is within the file's
 * own block reservation window range.
 *
 * If the reservation window is outside the goal allocation group, return 0;
 * grp_goal (given goal block) could be -1, which means no specific
 * goal block. In this case, always return 1.
 * If the goal block is within the reservation window, return 1;
 * otherwise, return 0;
 */
static int
goal_in_my_reservation(struct ext3_reserve_window *rsv, ext3_grpblk_t grp_goal,
			unsigned int group, struct super_block * sb)
{
	ext3_fsblk_t group_first_block, group_last_block;

	group_first_block = ext3_group_first_block_no(sb, group);
	group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1);

	if ((rsv->_rsv_start > group_last_block) ||
	    (rsv->_rsv_end < group_first_block))
		return 0;
	if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start)
		|| (grp_goal + group_first_block > rsv->_rsv_end)))
		return 0;
	return 1;
}

/**
 * search_reserve_window()
 * @rb_root:		root of reservation tree
 * @goal:		target allocation block
 *
 * Find the reserved window which includes the goal, or the previous one
 * if the goal is not in any window.
 * Returns NULL if there are no windows or if all windows start after the goal.
 */
static struct ext3_reserve_window_node *
search_reserve_window(struct rb_root *root, ext3_fsblk_t goal)
{
	struct rb_node *n = root->rb_node;
	struct ext3_reserve_window_node *rsv;

	if (!n)
		return NULL;

	do {
		rsv = rb_entry(n, struct ext3_reserve_window_node, rsv_node);

		if (goal < rsv->rsv_start)
			n = n->rb_left;
		else if (goal > rsv->rsv_end)
			n = n->rb_right;
		else
			return rsv;
	} while (n);
	/*
	 * We've fallen off the end of the tree: the goal wasn't inside
	 * any particular node.  OK, the previous node must be to one
	 * side of the interval containing the goal.  If it's the RHS,
	 * we need to back up one.
	 */
	if (rsv->rsv_start > goal) {
		n = rb_prev(&rsv->rsv_node);
		rsv = rb_entry(n, struct ext3_reserve_window_node, rsv_node);
	}
	return rsv;
}

/**
 * ext3_rsv_window_add() -- Insert a window to the block reservation rb tree.
 * @sb:			super block
 * @rsv:		reservation window to add
 *
 * Must be called with rsv_lock hold.
 */
void ext3_rsv_window_add(struct super_block *sb,
		    struct ext3_reserve_window_node *rsv)
{
	struct rb_root *root = &EXT3_SB(sb)->s_rsv_window_root;
	struct rb_node *node = &rsv->rsv_node;
	ext3_fsblk_t start = rsv->rsv_start;

	struct rb_node ** p = &root->rb_node;
	struct rb_node * parent = NULL;
	struct ext3_reserve_window_node *this;

	trace_ext3_rsv_window_add(sb, rsv);
	while (*p)
	{
		parent = *p;
		this = rb_entry(parent, struct ext3_reserve_window_node, rsv_node);

		if (start < this->rsv_start)
			p = &(*p)->rb_left;
		else if (start > this->rsv_end)
			p = &(*p)->rb_right;
		else {
			rsv_window_dump(root, 1);
			BUG();
		}
	}

	rb_link_node(node, parent, p);
	rb_insert_color(node, root);
}

/**
 * ext3_rsv_window_remove() -- unlink a window from the reservation rb tree
 * @sb:			super block
 * @rsv:		reservation window to remove
 *
 * Mark the block reservation window as not allocated, and unlink it
 * from the filesystem reservation window rb tree. Must be called with
 * rsv_lock hold.
 */
static void rsv_window_remove(struct super_block *sb,
			      struct ext3_reserve_window_node *rsv)
{
	rsv->rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	rsv->rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	rsv->rsv_alloc_hit = 0;
	rb_erase(&rsv->rsv_node, &EXT3_SB(sb)->s_rsv_window_root);
}

/*
 * rsv_is_empty() -- Check if the reservation window is allocated.
 * @rsv:		given reservation window to check
 *
 * returns 1 if the end block is EXT3_RESERVE_WINDOW_NOT_ALLOCATED.
 */
static inline int rsv_is_empty(struct ext3_reserve_window *rsv)
{
	/* a valid reservation end block could not be 0 */
	return rsv->_rsv_end == EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
}

/**
 * ext3_init_block_alloc_info()
 * @inode:		file inode structure
 *
 * Allocate and initialize the	reservation window structure, and
 * link the window to the ext3 inode structure at last
 *
 * The reservation window structure is only dynamically allocated
 * and linked to ext3 inode the first time the open file
 * needs a new block. So, before every ext3_new_block(s) call, for
 * regular files, we should check whether the reservation window
 * structure exists or not. In the latter case, this function is called.
 * Fail to do so will result in block reservation being turned off for that
 * open file.
 *
 * This function is called from ext3_get_blocks_handle(), also called
 * when setting the reservation window size through ioctl before the file
 * is open for write (needs block allocation).
 *
 * Needs truncate_mutex protection prior to call this function.
 */
void ext3_init_block_alloc_info(struct inode *inode)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	struct ext3_block_alloc_info *block_i;
	struct super_block *sb = inode->i_sb;

	block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
	if (block_i) {
		struct ext3_reserve_window_node *rsv = &block_i->rsv_window_node;

		rsv->rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
		rsv->rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;

		/*
		 * if filesystem is mounted with NORESERVATION, the goal
		 * reservation window size is set to zero to indicate
		 * block reservation is off
		 */
		if (!test_opt(sb, RESERVATION))
			rsv->rsv_goal_size = 0;
		else
			rsv->rsv_goal_size = EXT3_DEFAULT_RESERVE_BLOCKS;
		rsv->rsv_alloc_hit = 0;
		block_i->last_alloc_logical_block = 0;
		block_i->last_alloc_physical_block = 0;
	}
	ei->i_block_alloc_info = block_i;
}

/**
 * ext3_discard_reservation()
 * @inode:		inode
 *
 * Discard(free) block reservation window on last file close, or truncate
 * or at last iput().
 *
 * It is being called in three cases:
 *	ext3_release_file(): last writer close the file
 *	ext3_clear_inode(): last iput(), when nobody link to this file.
 *	ext3_truncate(): when the block indirect map is about to change.
 *
 */
void ext3_discard_reservation(struct inode *inode)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	struct ext3_block_alloc_info *block_i = ei->i_block_alloc_info;
	struct ext3_reserve_window_node *rsv;
	spinlock_t *rsv_lock = &EXT3_SB(inode->i_sb)->s_rsv_window_lock;

	if (!block_i)
		return;

	rsv = &block_i->rsv_window_node;
	if (!rsv_is_empty(&rsv->rsv_window)) {
		spin_lock(rsv_lock);
		if (!rsv_is_empty(&rsv->rsv_window)) {
			trace_ext3_discard_reservation(inode, rsv);
			rsv_window_remove(inode->i_sb, rsv);
		}
		spin_unlock(rsv_lock);
	}
}

/**
 * ext3_free_blocks_sb() -- Free given blocks and update quota
 * @handle:			handle to this transaction
 * @sb:				super block
 * @block:			start physcial block to free
 * @count:			number of blocks to free
 * @pdquot_freed_blocks:	pointer to quota
 */
void ext3_free_blocks_sb(handle_t *handle, struct super_block *sb,
			 ext3_fsblk_t block, unsigned long count,
			 unsigned long *pdquot_freed_blocks)
{
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *gd_bh;
	unsigned long block_group;
	ext3_grpblk_t bit;
	unsigned long i;
	unsigned long overflow;
	struct ext3_group_desc * desc;
	struct ext3_super_block * es;
	struct ext3_sb_info *sbi;
	int err = 0, ret;
	ext3_grpblk_t group_freed;

	*pdquot_freed_blocks = 0;
	sbi = EXT3_SB(sb);
	es = sbi->s_es;
	if (block < le32_to_cpu(es->s_first_data_block) ||
	    block + count < block ||
	    block + count > le32_to_cpu(es->s_blocks_count)) {
		ext3_error (sb, "ext3_free_blocks",
			    "Freeing blocks not in datazone - "
			    "block = "E3FSBLK", count = %lu", block, count);
		goto error_return;
	}

	ext3_debug ("freeing block(s) %lu-%lu\n", block, block + count - 1);

do_more:
	overflow = 0;
	block_group = (block - le32_to_cpu(es->s_first_data_block)) /
		      EXT3_BLOCKS_PER_GROUP(sb);
	bit = (block - le32_to_cpu(es->s_first_data_block)) %
		      EXT3_BLOCKS_PER_GROUP(sb);
	/*
	 * Check to see if we are freeing blocks across a group
	 * boundary.
	 */
	if (bit + count > EXT3_BLOCKS_PER_GROUP(sb)) {
		overflow = bit + count - EXT3_BLOCKS_PER_GROUP(sb);
		count -= overflow;
	}
	brelse(bitmap_bh);
	bitmap_bh = read_block_bitmap(sb, block_group);
	if (!bitmap_bh)
		goto error_return;
	desc = ext3_get_group_desc (sb, block_group, &gd_bh);
	if (!desc)
		goto error_return;

	if (in_range (le32_to_cpu(desc->bg_block_bitmap), block, count) ||
	    in_range (le32_to_cpu(desc->bg_inode_bitmap), block, count) ||
	    in_range (block, le32_to_cpu(desc->bg_inode_table),
		      sbi->s_itb_per_group) ||
	    in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table),
		      sbi->s_itb_per_group)) {
		ext3_error (sb, "ext3_free_blocks",
			    "Freeing blocks in system zones - "
			    "Block = "E3FSBLK", count = %lu",
			    block, count);
		goto error_return;
	}

	/*
	 * We are about to start releasing blocks in the bitmap,
	 * so we need undo access.
	 */
	/* @@@ check errors */
	BUFFER_TRACE(bitmap_bh, "getting undo access");
	err = ext3_journal_get_undo_access(handle, bitmap_bh);
	if (err)
		goto error_return;

	/*
	 * We are about to modify some metadata.  Call the journal APIs
	 * to unshare ->b_data if a currently-committing transaction is
	 * using it
	 */
	BUFFER_TRACE(gd_bh, "get_write_access");
	err = ext3_journal_get_write_access(handle, gd_bh);
	if (err)
		goto error_return;

	jbd_lock_bh_state(bitmap_bh);

	for (i = 0, group_freed = 0; i < count; i++) {
		/*
		 * An HJ special.  This is expensive...
		 */
#ifdef CONFIG_JBD_DEBUG
		jbd_unlock_bh_state(bitmap_bh);
		{
			struct buffer_head *debug_bh;
			debug_bh = sb_find_get_block(sb, block + i);
			if (debug_bh) {
				BUFFER_TRACE(debug_bh, "Deleted!");
				if (!bh2jh(bitmap_bh)->b_committed_data)
					BUFFER_TRACE(debug_bh,
						"No committed data in bitmap");
				BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap");
				__brelse(debug_bh);
			}
		}
		jbd_lock_bh_state(bitmap_bh);
#endif
		if (need_resched()) {
			jbd_unlock_bh_state(bitmap_bh);
			cond_resched();
			jbd_lock_bh_state(bitmap_bh);
		}
		/* @@@ This prevents newly-allocated data from being
		 * freed and then reallocated within the same
		 * transaction.
		 *
		 * Ideally we would want to allow that to happen, but to
		 * do so requires making journal_forget() capable of
		 * revoking the queued write of a data block, which
		 * implies blocking on the journal lock.  *forget()
		 * cannot block due to truncate races.
		 *
		 * Eventually we can fix this by making journal_forget()
		 * return a status indicating whether or not it was able
		 * to revoke the buffer.  On successful revoke, it is
		 * safe not to set the allocation bit in the committed
		 * bitmap, because we know that there is no outstanding
		 * activity on the buffer any more and so it is safe to
		 * reallocate it.
		 */
		BUFFER_TRACE(bitmap_bh, "set in b_committed_data");
		J_ASSERT_BH(bitmap_bh,
				bh2jh(bitmap_bh)->b_committed_data != NULL);
		ext3_set_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i,
				bh2jh(bitmap_bh)->b_committed_data);

		/*
		 * We clear the bit in the bitmap after setting the committed
		 * data bit, because this is the reverse order to that which
		 * the allocator uses.
		 */
		BUFFER_TRACE(bitmap_bh, "clear bit");
		if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
						bit + i, bitmap_bh->b_data)) {
			jbd_unlock_bh_state(bitmap_bh);
			ext3_error(sb, __func__,
				"bit already cleared for block "E3FSBLK,
				 block + i);
			jbd_lock_bh_state(bitmap_bh);
			BUFFER_TRACE(bitmap_bh, "bit already cleared");
		} else {
			group_freed++;
		}
	}
	jbd_unlock_bh_state(bitmap_bh);

	spin_lock(sb_bgl_lock(sbi, block_group));
	le16_add_cpu(&desc->bg_free_blocks_count, group_freed);
	spin_unlock(sb_bgl_lock(sbi, block_group));
	percpu_counter_add(&sbi->s_freeblocks_counter, count);

	/* We dirtied the bitmap block */
	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
	err = ext3_journal_dirty_metadata(handle, bitmap_bh);

	/* And the group descriptor block */
	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
	ret = ext3_journal_dirty_metadata(handle, gd_bh);
	if (!err) err = ret;
	*pdquot_freed_blocks += group_freed;

	if (overflow && !err) {
		block += count;
		count = overflow;
		goto do_more;
	}

error_return:
	brelse(bitmap_bh);
	ext3_std_error(sb, err);
	return;
}

/**
 * ext3_free_blocks() -- Free given blocks and update quota
 * @handle:		handle for this transaction
 * @inode:		inode
 * @block:		start physical block to free
 * @count:		number of blocks to count
 */
void ext3_free_blocks(handle_t *handle, struct inode *inode,
			ext3_fsblk_t block, unsigned long count)
{
	struct super_block *sb = inode->i_sb;
	unsigned long dquot_freed_blocks;

	trace_ext3_free_blocks(inode, block, count);
	ext3_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks);
	if (dquot_freed_blocks)
		dquot_free_block(inode, dquot_freed_blocks);
	return;
}

/**
 * ext3_test_allocatable()
 * @nr:			given allocation block group
 * @bh:			bufferhead contains the bitmap of the given block group
 *
 * For ext3 allocations, we must not reuse any blocks which are
 * allocated in the bitmap buffer's "last committed data" copy.  This
 * prevents deletes from freeing up the page for reuse until we have
 * committed the delete transaction.
 *
 * If we didn't do this, then deleting something and reallocating it as
 * data would allow the old block to be overwritten before the
 * transaction committed (because we force data to disk before commit).
 * This would lead to corruption if we crashed between overwriting the
 * data and committing the delete.
 *
 * @@@ We may want to make this allocation behaviour conditional on
 * data-writes at some point, and disable it for metadata allocations or
 * sync-data inodes.
 */
static int ext3_test_allocatable(ext3_grpblk_t nr, struct buffer_head *bh)
{
	int ret;
	struct journal_head *jh = bh2jh(bh);

	if (ext3_test_bit(nr, bh->b_data))
		return 0;

	jbd_lock_bh_state(bh);
	if (!jh->b_committed_data)
		ret = 1;
	else
		ret = !ext3_test_bit(nr, jh->b_committed_data);
	jbd_unlock_bh_state(bh);
	return ret;
}

/**
 * bitmap_search_next_usable_block()
 * @start:		the starting block (group relative) of the search
 * @bh:			bufferhead contains the block group bitmap
 * @maxblocks:		the ending block (group relative) of the reservation
 *
 * The bitmap search --- search forward alternately through the actual
 * bitmap on disk and the last-committed copy in journal, until we find a
 * bit free in both bitmaps.
 */
static ext3_grpblk_t
bitmap_search_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh,
					ext3_grpblk_t maxblocks)
{
	ext3_grpblk_t next;
	struct journal_head *jh = bh2jh(bh);

	while (start < maxblocks) {
		next = ext3_find_next_zero_bit(bh->b_data, maxblocks, start);
		if (next >= maxblocks)
			return -1;
		if (ext3_test_allocatable(next, bh))
			return next;
		jbd_lock_bh_state(bh);
		if (jh->b_committed_data)
			start = ext3_find_next_zero_bit(jh->b_committed_data,
							maxblocks, next);
		jbd_unlock_bh_state(bh);
	}
	return -1;
}

/**
 * find_next_usable_block()
 * @start:		the starting block (group relative) to find next
 *			allocatable block in bitmap.
 * @bh:			bufferhead contains the block group bitmap
 * @maxblocks:		the ending block (group relative) for the search
 *
 * Find an allocatable block in a bitmap.  We honor both the bitmap and
 * its last-committed copy (if that exists), and perform the "most
 * appropriate allocation" algorithm of looking for a free block near
 * the initial goal; then for a free byte somewhere in the bitmap; then
 * for any free bit in the bitmap.
 */
static ext3_grpblk_t
find_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh,
			ext3_grpblk_t maxblocks)
{
	ext3_grpblk_t here, next;
	char *p, *r;

	if (start > 0) {
		/*
		 * The goal was occupied; search forward for a free
		 * block within the next XX blocks.
		 *
		 * end_goal is more or less random, but it has to be
		 * less than EXT3_BLOCKS_PER_GROUP. Aligning up to the
		 * next 64-bit boundary is simple..
		 */
		ext3_grpblk_t end_goal = (start + 63) & ~63;
		if (end_goal > maxblocks)
			end_goal = maxblocks;
		here = ext3_find_next_zero_bit(bh->b_data, end_goal, start);
		if (here < end_goal && ext3_test_allocatable(here, bh))
			return here;
		ext3_debug("Bit not found near goal\n");
	}

	here = start;
	if (here < 0)
		here = 0;

	p = bh->b_data + (here >> 3);
	r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3));
	next = (r - bh->b_data) << 3;

	if (next < maxblocks && next >= start && ext3_test_allocatable(next, bh))
		return next;

	/*
	 * The bitmap search --- search forward alternately through the actual
	 * bitmap and the last-committed copy until we find a bit free in
	 * both
	 */
	here = bitmap_search_next_usable_block(here, bh, maxblocks);
	return here;
}

/**
 * claim_block()
 * @lock:		the spin lock for this block group
 * @block:		the free block (group relative) to allocate
 * @bh:			the buffer_head contains the block group bitmap
 *
 * We think we can allocate this block in this bitmap.  Try to set the bit.
 * If that succeeds then check that nobody has allocated and then freed the
 * block since we saw that is was not marked in b_committed_data.  If it _was_
 * allocated and freed then clear the bit in the bitmap again and return
 * zero (failure).
 */
static inline int
claim_block(spinlock_t *lock, ext3_grpblk_t block, struct buffer_head *bh)
{
	struct journal_head *jh = bh2jh(bh);
	int ret;

	if (ext3_set_bit_atomic(lock, block, bh->b_data))
		return 0;
	jbd_lock_bh_state(bh);
	if (jh->b_committed_data && ext3_test_bit(block,jh->b_committed_data)) {
		ext3_clear_bit_atomic(lock, block, bh->b_data);
		ret = 0;
	} else {
		ret = 1;
	}
	jbd_unlock_bh_state(bh);
	return ret;
}

/**
 * ext3_try_to_allocate()
 * @sb:			superblock
 * @handle:		handle to this transaction
 * @group:		given allocation block group
 * @bitmap_bh:		bufferhead holds the block bitmap
 * @grp_goal:		given target block within the group
 * @count:		target number of blocks to allocate
 * @my_rsv:		reservation window
 *
 * Attempt to allocate blocks within a give range. Set the range of allocation
 * first, then find the first free bit(s) from the bitmap (within the range),
 * and at last, allocate the blocks by claiming the found free bit as allocated.
 *
 * To set the range of this allocation:
 *	if there is a reservation window, only try to allocate block(s) from the
 *	file's own reservation window;
 *	Otherwise, the allocation range starts from the give goal block, ends at
 *	the block group's last block.
 *
 * If we failed to allocate the desired block then we may end up crossing to a
 * new bitmap.  In that case we must release write access to the old one via
 * ext3_journal_release_buffer(), else we'll run out of credits.
 */
static ext3_grpblk_t
ext3_try_to_allocate(struct super_block *sb, handle_t *handle, int group,
			struct buffer_head *bitmap_bh, ext3_grpblk_t grp_goal,
			unsigned long *count, struct ext3_reserve_window *my_rsv)
{
	ext3_fsblk_t group_first_block;
	ext3_grpblk_t start, end;
	unsigned long num = 0;

	/* we do allocation within the reservation window if we have a window */
	if (my_rsv) {
		group_first_block = ext3_group_first_block_no(sb, group);
		if (my_rsv->_rsv_start >= group_first_block)
			start = my_rsv->_rsv_start - group_first_block;
		else
			/* reservation window cross group boundary */
			start = 0;
		end = my_rsv->_rsv_end - group_first_block + 1;
		if (end > EXT3_BLOCKS_PER_GROUP(sb))
			/* reservation window crosses group boundary */
			end = EXT3_BLOCKS_PER_GROUP(sb);
		if ((start <= grp_goal) && (grp_goal < end))
			start = grp_goal;
		else
			grp_goal = -1;
	} else {
		if (grp_goal > 0)
			start = grp_goal;
		else
			start = 0;
		end = EXT3_BLOCKS_PER_GROUP(sb);
	}

	BUG_ON(start > EXT3_BLOCKS_PER_GROUP(sb));

repeat:
	if (grp_goal < 0 || !ext3_test_allocatable(grp_goal, bitmap_bh)) {
		grp_goal = find_next_usable_block(start, bitmap_bh, end);
		if (grp_goal < 0)
			goto fail_access;
		if (!my_rsv) {
			int i;

			for (i = 0; i < 7 && grp_goal > start &&
					ext3_test_allocatable(grp_goal - 1,
								bitmap_bh);
					i++, grp_goal--)
				;
		}
	}
	start = grp_goal;

	if (!claim_block(sb_bgl_lock(EXT3_SB(sb), group),
		grp_goal, bitmap_bh)) {
		/*
		 * The block was allocated by another thread, or it was
		 * allocated and then freed by another thread
		 */
		start++;
		grp_goal++;
		if (start >= end)
			goto fail_access;
		goto repeat;
	}
	num++;
	grp_goal++;
	while (num < *count && grp_goal < end
		&& ext3_test_allocatable(grp_goal, bitmap_bh)
		&& claim_block(sb_bgl_lock(EXT3_SB(sb), group),
				grp_goal, bitmap_bh)) {
		num++;
		grp_goal++;
	}
	*count = num;
	return grp_goal - num;
fail_access:
	*count = num;
	return -1;
}

/**
 *	find_next_reservable_window():
 *		find a reservable space within the given range.
 *		It does not allocate the reservation window for now:
 *		alloc_new_reservation() will do the work later.
 *
 *	@search_head: the head of the searching list;
 *		This is not necessarily the list head of the whole filesystem
 *
 *		We have both head and start_block to assist the search
 *		for the reservable space. The list starts from head,
 *		but we will shift to the place where start_block is,
 *		then start from there, when looking for a reservable space.
 *
 *	@my_rsv: the reservation window
 *
 *	@sb: the super block
 *
 *	@start_block: the first block we consider to start
 *			the real search from
 *
 *	@last_block:
 *		the maximum block number that our goal reservable space
 *		could start from. This is normally the last block in this
 *		group. The search will end when we found the start of next
 *		possible reservable space is out of this boundary.
 *		This could handle the cross boundary reservation window
 *		request.
 *
 *	basically we search from the given range, rather than the whole
 *	reservation double linked list, (start_block, last_block)
 *	to find a free region that is of my size and has not
 *	been reserved.
 *
 */
static int find_next_reservable_window(
				struct ext3_reserve_window_node *search_head,
				struct ext3_reserve_window_node *my_rsv,
				struct super_block * sb,
				ext3_fsblk_t start_block,
				ext3_fsblk_t last_block)
{
	struct rb_node *next;
	struct ext3_reserve_window_node *rsv, *prev;
	ext3_fsblk_t cur;
	int size = my_rsv->rsv_goal_size;

	/* TODO: make the start of the reservation window byte-aligned */
	/* cur = *start_block & ~7;*/
	cur = start_block;
	rsv = search_head;
	if (!rsv)
		return -1;

	while (1) {
		if (cur <= rsv->rsv_end)
			cur = rsv->rsv_end + 1;

		/* TODO?
		 * in the case we could not find a reservable space
		 * that is what is expected, during the re-search, we could
		 * remember what's the largest reservable space we could have
		 * and return that one.
		 *
		 * For now it will fail if we could not find the reservable
		 * space with expected-size (or more)...
		 */
		if (cur > last_block)
			return -1;		/* fail */

		prev = rsv;
		next = rb_next(&rsv->rsv_node);
		rsv = rb_entry(next,struct ext3_reserve_window_node,rsv_node);

		/*
		 * Reached the last reservation, we can just append to the
		 * previous one.
		 */
		if (!next)
			break;

		if (cur + size <= rsv->rsv_start) {
			/*
			 * Found a reserveable space big enough.  We could
			 * have a reservation across the group boundary here
			 */
			break;
		}
	}
	/*
	 * we come here either :
	 * when we reach the end of the whole list,
	 * and there is empty reservable space after last entry in the list.
	 * append it to the end of the list.
	 *
	 * or we found one reservable space in the middle of the list,
	 * return the reservation window that we could append to.
	 * succeed.
	 */

	if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window)))
		rsv_window_remove(sb, my_rsv);

	/*
	 * Let's book the whole available window for now.  We will check the
	 * disk bitmap later and then, if there are free blocks then we adjust
	 * the window size if it's larger than requested.
	 * Otherwise, we will remove this node from the tree next time
	 * call find_next_reservable_window.
	 */
	my_rsv->rsv_start = cur;
	my_rsv->rsv_end = cur + size - 1;
	my_rsv->rsv_alloc_hit = 0;

	if (prev != my_rsv)
		ext3_rsv_window_add(sb, my_rsv);

	return 0;
}

/**
 *	alloc_new_reservation()--allocate a new reservation window
 *
 *		To make a new reservation, we search part of the filesystem
 *		reservation list (the list that inside the group). We try to
 *		allocate a new reservation window near the allocation goal,
 *		or the beginning of the group, if there is no goal.
 *
 *		We first find a reservable space after the goal, then from
 *		there, we check the bitmap for the first free block after
 *		it. If there is no free block until the end of group, then the
 *		whole group is full, we failed. Otherwise, check if the free
 *		block is inside the expected reservable space, if so, we
 *		succeed.
 *		If the first free block is outside the reservable space, then
 *		start from the first free block, we search for next available
 *		space, and go on.
 *
 *	on succeed, a new reservation will be found and inserted into the list
 *	It contains at least one free block, and it does not overlap with other
 *	reservation windows.
 *
 *	failed: we failed to find a reservation window in this group
 *
 *	@my_rsv: the reservation window
 *
 *	@grp_goal: The goal (group-relative).  It is where the search for a
 *		free reservable space should start from.
 *		if we have a grp_goal(grp_goal >0 ), then start from there,
 *		no grp_goal(grp_goal = -1), we start from the first block
 *		of the group.
 *
 *	@sb: the super block
 *	@group: the group we are trying to allocate in
 *	@bitmap_bh: the block group block bitmap
 *
 */
static int alloc_new_reservation(struct ext3_reserve_window_node *my_rsv,
		ext3_grpblk_t grp_goal, struct super_block *sb,
		unsigned int group, struct buffer_head *bitmap_bh)
{
	struct ext3_reserve_window_node *search_head;
	ext3_fsblk_t group_first_block, group_end_block, start_block;
	ext3_grpblk_t first_free_block;
	struct rb_root *fs_rsv_root = &EXT3_SB(sb)->s_rsv_window_root;
	unsigned long size;
	int ret;
	spinlock_t *rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock;

	group_first_block = ext3_group_first_block_no(sb, group);
	group_end_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1);

	if (grp_goal < 0)
		start_block = group_first_block;
	else
		start_block = grp_goal + group_first_block;

	trace_ext3_alloc_new_reservation(sb, start_block);
	size = my_rsv->rsv_goal_size;

	if (!rsv_is_empty(&my_rsv->rsv_window)) {
		/*
		 * if the old reservation is cross group boundary
		 * and if the goal is inside the old reservation window,
		 * we will come here when we just failed to allocate from
		 * the first part of the window. We still have another part
		 * that belongs to the next group. In this case, there is no
		 * point to discard our window and try to allocate a new one
		 * in this group(which will fail). we should
		 * keep the reservation window, just simply move on.
		 *
		 * Maybe we could shift the start block of the reservation
		 * window to the first block of next group.
		 */

		if ((my_rsv->rsv_start <= group_end_block) &&
				(my_rsv->rsv_end > group_end_block) &&
				(start_block >= my_rsv->rsv_start))
			return -1;

		if ((my_rsv->rsv_alloc_hit >
		     (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) {
			/*
			 * if the previously allocation hit ratio is
			 * greater than 1/2, then we double the size of
			 * the reservation window the next time,
			 * otherwise we keep the same size window
			 */
			size = size * 2;
			if (size > EXT3_MAX_RESERVE_BLOCKS)
				size = EXT3_MAX_RESERVE_BLOCKS;
			my_rsv->rsv_goal_size= size;
		}
	}

	spin_lock(rsv_lock);
	/*
	 * shift the search start to the window near the goal block
	 */
	search_head = search_reserve_window(fs_rsv_root, start_block);

	/*
	 * find_next_reservable_window() simply finds a reservable window
	 * inside the given range(start_block, group_end_block).
	 *
	 * To make sure the reservation window has a free bit inside it, we
	 * need to check the bitmap after we found a reservable window.
	 */
retry:
	ret = find_next_reservable_window(search_head, my_rsv, sb,
						start_block, group_end_block);

	if (ret == -1) {
		if (!rsv_is_empty(&my_rsv->rsv_window))
			rsv_window_remove(sb, my_rsv);
		spin_unlock(rsv_lock);
		return -1;
	}

	/*
	 * On success, find_next_reservable_window() returns the
	 * reservation window where there is a reservable space after it.
	 * Before we reserve this reservable space, we need
	 * to make sure there is at least a free block inside this region.
	 *
	 * searching the first free bit on the block bitmap and copy of
	 * last committed bitmap alternatively, until we found a allocatable
	 * block. Search start from the start block of the reservable space
	 * we just found.
	 */
	spin_unlock(rsv_lock);
	first_free_block = bitmap_search_next_usable_block(
			my_rsv->rsv_start - group_first_block,
			bitmap_bh, group_end_block - group_first_block + 1);

	if (first_free_block < 0) {
		/*
		 * no free block left on the bitmap, no point
		 * to reserve the space. return failed.
		 */
		spin_lock(rsv_lock);
		if (!rsv_is_empty(&my_rsv->rsv_window))
			rsv_window_remove(sb, my_rsv);
		spin_unlock(rsv_lock);
		return -1;		/* failed */
	}

	start_block = first_free_block + group_first_block;
	/*
	 * check if the first free block is within the
	 * free space we just reserved
	 */
	if (start_block >= my_rsv->rsv_start &&
	    start_block <= my_rsv->rsv_end) {
		trace_ext3_reserved(sb, start_block, my_rsv);
		return 0;		/* success */
	}
	/*
	 * if the first free bit we found is out of the reservable space
	 * continue search for next reservable space,
	 * start from where the free block is,
	 * we also shift the list head to where we stopped last time
	 */
	search_head = my_rsv;
	spin_lock(rsv_lock);
	goto retry;
}

/**
 * try_to_extend_reservation()
 * @my_rsv:		given reservation window
 * @sb:			super block
 * @size:		the delta to extend
 *
 * Attempt to expand the reservation window large enough to have
 * required number of free blocks
 *
 * Since ext3_try_to_allocate() will always allocate blocks within
 * the reservation window range, if the window size is too small,
 * multiple blocks allocation has to stop at the end of the reservation
 * window. To make this more efficient, given the total number of
 * blocks needed and the current size of the window, we try to
 * expand the reservation window size if necessary on a best-effort
 * basis before ext3_new_blocks() tries to allocate blocks,
 */
static void try_to_extend_reservation(struct ext3_reserve_window_node *my_rsv,
			struct super_block *sb, int size)
{
	struct ext3_reserve_window_node *next_rsv;
	struct rb_node *next;
	spinlock_t *rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock;

	if (!spin_trylock(rsv_lock))
		return;

	next = rb_next(&my_rsv->rsv_node);

	if (!next)
		my_rsv->rsv_end += size;
	else {
		next_rsv = rb_entry(next, struct ext3_reserve_window_node, rsv_node);

		if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
			my_rsv->rsv_end += size;
		else
			my_rsv->rsv_end = next_rsv->rsv_start - 1;
	}
	spin_unlock(rsv_lock);
}

/**
 * ext3_try_to_allocate_with_rsv()
 * @sb:			superblock
 * @handle:		handle to this transaction
 * @group:		given allocation block group
 * @bitmap_bh:		bufferhead holds the block bitmap
 * @grp_goal:		given target block within the group
 * @my_rsv:		reservation window
 * @count:		target number of blocks to allocate
 * @errp:		pointer to store the error code
 *
 * This is the main function used to allocate a new block and its reservation
 * window.
 *
 * Each time when a new block allocation is need, first try to allocate from
 * its own reservation.  If it does not have a reservation window, instead of
 * looking for a free bit on bitmap first, then look up the reservation list to
 * see if it is inside somebody else's reservation window, we try to allocate a
 * reservation window for it starting from the goal first. Then do the block
 * allocation within the reservation window.
 *
 * This will avoid keeping on searching the reservation list again and
 * again when somebody is looking for a free block (without
 * reservation), and there are lots of free blocks, but they are all
 * being reserved.
 *
 * We use a red-black tree for the per-filesystem reservation list.
 *
 */
static ext3_grpblk_t
ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
			unsigned int group, struct buffer_head *bitmap_bh,
			ext3_grpblk_t grp_goal,
			struct ext3_reserve_window_node * my_rsv,
			unsigned long *count, int *errp)
{
	ext3_fsblk_t group_first_block, group_last_block;
	ext3_grpblk_t ret = 0;
	int fatal;
	unsigned long num = *count;

	*errp = 0;

	/*
	 * Make sure we use undo access for the bitmap, because it is critical
	 * that we do the frozen_data COW on bitmap buffers in all cases even
	 * if the buffer is in BJ_Forget state in the committing transaction.
	 */
	BUFFER_TRACE(bitmap_bh, "get undo access for new block");
	fatal = ext3_journal_get_undo_access(handle, bitmap_bh);
	if (fatal) {
		*errp = fatal;
		return -1;
	}

	/*
	 * we don't deal with reservation when
	 * filesystem is mounted without reservation
	 * or the file is not a regular file
	 * or last attempt to allocate a block with reservation turned on failed
	 */
	if (my_rsv == NULL ) {
		ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh,
						grp_goal, count, NULL);
		goto out;
	}
	/*
	 * grp_goal is a group relative block number (if there is a goal)
	 * 0 <= grp_goal < EXT3_BLOCKS_PER_GROUP(sb)
	 * first block is a filesystem wide block number
	 * first block is the block number of the first block in this group
	 */
	group_first_block = ext3_group_first_block_no(sb, group);
	group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1);

	/*
	 * Basically we will allocate a new block from inode's reservation
	 * window.
	 *
	 * We need to allocate a new reservation window, if:
	 * a) inode does not have a reservation window; or
	 * b) last attempt to allocate a block from existing reservation
	 *    failed; or
	 * c) we come here with a goal and with a reservation window
	 *
	 * We do not need to allocate a new reservation window if we come here
	 * at the beginning with a goal and the goal is inside the window, or
	 * we don't have a goal but already have a reservation window.
	 * then we could go to allocate from the reservation window directly.
	 */
	while (1) {
		if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) ||
			!goal_in_my_reservation(&my_rsv->rsv_window,
						grp_goal, group, sb)) {
			if (my_rsv->rsv_goal_size < *count)
				my_rsv->rsv_goal_size = *count;
			ret = alloc_new_reservation(my_rsv, grp_goal, sb,
							group, bitmap_bh);
			if (ret < 0)
				break;			/* failed */

			if (!goal_in_my_reservation(&my_rsv->rsv_window,
							grp_goal, group, sb))
				grp_goal = -1;
		} else if (grp_goal >= 0) {
			int curr = my_rsv->rsv_end -
					(grp_goal + group_first_block) + 1;

			if (curr < *count)
				try_to_extend_reservation(my_rsv, sb,
							*count - curr);
		}

		if ((my_rsv->rsv_start > group_last_block) ||
				(my_rsv->rsv_end < group_first_block)) {
			rsv_window_dump(&EXT3_SB(sb)->s_rsv_window_root, 1);
			BUG();
		}
		ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh,
					   grp_goal, &num, &my_rsv->rsv_window);
		if (ret >= 0) {
			my_rsv->rsv_alloc_hit += num;
			*count = num;
			break;				/* succeed */
		}
		num = *count;
	}
out:
	if (ret >= 0) {
		BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for "
					"bitmap block");
		fatal = ext3_journal_dirty_metadata(handle, bitmap_bh);
		if (fatal) {
			*errp = fatal;
			return -1;
		}
		return ret;
	}

	BUFFER_TRACE(bitmap_bh, "journal_release_buffer");
	ext3_journal_release_buffer(handle, bitmap_bh);
	return ret;
}

/**
 * ext3_has_free_blocks()
 * @sbi:		in-core super block structure.
 *
 * Check if filesystem has at least 1 free block available for allocation.
 */
static int ext3_has_free_blocks(struct ext3_sb_info *sbi, int use_reservation)
{
	ext3_fsblk_t free_blocks, root_blocks;

	free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
	root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
	if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
		!use_reservation && sbi->s_resuid != current_fsuid() &&
		(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
		return 0;
	}
	return 1;
}

/**
 * ext3_should_retry_alloc()
 * @sb:			super block
 * @retries		number of attemps has been made
 *
 * ext3_should_retry_alloc() is called when ENOSPC is returned, and if
 * it is profitable to retry the operation, this function will wait
 * for the current or committing transaction to complete, and then
 * return TRUE.
 *
 * if the total number of retries exceed three times, return FALSE.
 */
int ext3_should_retry_alloc(struct super_block *sb, int *retries)
{
	if (!ext3_has_free_blocks(EXT3_SB(sb), 0) || (*retries)++ > 3)
		return 0;

	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);

	return journal_force_commit_nested(EXT3_SB(sb)->s_journal);
}

/**
 * ext3_new_blocks() -- core block(s) allocation function
 * @handle:		handle to this transaction
 * @inode:		file inode
 * @goal:		given target block(filesystem wide)
 * @count:		target number of blocks to allocate
 * @errp:		error code
 *
 * ext3_new_blocks uses a goal block to assist allocation.  It tries to
 * allocate block(s) from the block group contains the goal block first. If that
 * fails, it will try to allocate block(s) from other block groups without
 * any specific goal block.
 *
 */
ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode,
			ext3_fsblk_t goal, unsigned long *count, int *errp)
{
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *gdp_bh;
	int group_no;
	int goal_group;
	ext3_grpblk_t grp_target_blk;	/* blockgroup relative goal block */
	ext3_grpblk_t grp_alloc_blk;	/* blockgroup-relative allocated block*/
	ext3_fsblk_t ret_block;		/* filesyetem-wide allocated block */
	int bgi;			/* blockgroup iteration index */
	int fatal = 0, err;
	int performed_allocation = 0;
	ext3_grpblk_t free_blocks;	/* number of free blocks in a group */
	struct super_block *sb;
	struct ext3_group_desc *gdp;
	struct ext3_super_block *es;
	struct ext3_sb_info *sbi;
	struct ext3_reserve_window_node *my_rsv = NULL;
	struct ext3_block_alloc_info *block_i;
	unsigned short windowsz = 0;
#ifdef EXT3FS_DEBUG
	static int goal_hits, goal_attempts;
#endif
	unsigned long ngroups;
	unsigned long num = *count;

	*errp = -ENOSPC;
	sb = inode->i_sb;

	/*
	 * Check quota for allocation of this block.
	 */
	err = dquot_alloc_block(inode, num);
	if (err) {
		*errp = err;
		return 0;
	}

	trace_ext3_request_blocks(inode, goal, num);

	sbi = EXT3_SB(sb);
	es = sbi->s_es;
	ext3_debug("goal=%lu.\n", goal);
	/*
	 * Allocate a block from reservation only when
	 * filesystem is mounted with reservation(default,-o reservation), and
	 * it's a regular file, and
	 * the desired window size is greater than 0 (One could use ioctl
	 * command EXT3_IOC_SETRSVSZ to set the window size to 0 to turn off
	 * reservation on that particular file)
	 */
	block_i = EXT3_I(inode)->i_block_alloc_info;
	if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
		my_rsv = &block_i->rsv_window_node;

	if (!ext3_has_free_blocks(sbi, IS_NOQUOTA(inode))) {
		*errp = -ENOSPC;
		goto out;
	}

	/*
	 * First, test whether the goal block is free.
	 */
	if (goal < le32_to_cpu(es->s_first_data_block) ||
	    goal >= le32_to_cpu(es->s_blocks_count))
		goal = le32_to_cpu(es->s_first_data_block);
	group_no = (goal - le32_to_cpu(es->s_first_data_block)) /
			EXT3_BLOCKS_PER_GROUP(sb);
	goal_group = group_no;
retry_alloc:
	gdp = ext3_get_group_desc(sb, group_no, &gdp_bh);
	if (!gdp)
		goto io_error;

	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
	/*
	 * if there is not enough free blocks to make a new resevation
	 * turn off reservation for this allocation
	 */
	if (my_rsv && (free_blocks < windowsz)
		&& (free_blocks > 0)
		&& (rsv_is_empty(&my_rsv->rsv_window)))
		my_rsv = NULL;

	if (free_blocks > 0) {
		grp_target_blk = ((goal - le32_to_cpu(es->s_first_data_block)) %
				EXT3_BLOCKS_PER_GROUP(sb));
		bitmap_bh = read_block_bitmap(sb, group_no);
		if (!bitmap_bh)
			goto io_error;
		grp_alloc_blk = ext3_try_to_allocate_with_rsv(sb, handle,
					group_no, bitmap_bh, grp_target_blk,
					my_rsv,	&num, &fatal);
		if (fatal)
			goto out;
		if (grp_alloc_blk >= 0)
			goto allocated;
	}

	ngroups = EXT3_SB(sb)->s_groups_count;
	smp_rmb();

	/*
	 * Now search the rest of the groups.  We assume that
	 * group_no and gdp correctly point to the last group visited.
	 */
	for (bgi = 0; bgi < ngroups; bgi++) {
		group_no++;
		if (group_no >= ngroups)
			group_no = 0;
		gdp = ext3_get_group_desc(sb, group_no, &gdp_bh);
		if (!gdp)
			goto io_error;
		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
		/*
		 * skip this group (and avoid loading bitmap) if there
		 * are no free blocks
		 */
		if (!free_blocks)
			continue;
		/*
		 * skip this group if the number of
		 * free blocks is less than half of the reservation
		 * window size.
		 */
		if (my_rsv && (free_blocks <= (windowsz/2)))
			continue;

		brelse(bitmap_bh);
		bitmap_bh = read_block_bitmap(sb, group_no);
		if (!bitmap_bh)
			goto io_error;
		/*
		 * try to allocate block(s) from this group, without a goal(-1).
		 */
		grp_alloc_blk = ext3_try_to_allocate_with_rsv(sb, handle,
					group_no, bitmap_bh, -1, my_rsv,
					&num, &fatal);
		if (fatal)
			goto out;
		if (grp_alloc_blk >= 0)
			goto allocated;
	}
	/*
	 * We may end up a bogus earlier ENOSPC error due to
	 * filesystem is "full" of reservations, but
	 * there maybe indeed free blocks available on disk
	 * In this case, we just forget about the reservations
	 * just do block allocation as without reservations.
	 */
	if (my_rsv) {
		my_rsv = NULL;
		windowsz = 0;
		group_no = goal_group;
		goto retry_alloc;
	}
	/* No space left on the device */
	*errp = -ENOSPC;
	goto out;

allocated:

	ext3_debug("using block group %d(%d)\n",
			group_no, gdp->bg_free_blocks_count);

	BUFFER_TRACE(gdp_bh, "get_write_access");
	fatal = ext3_journal_get_write_access(handle, gdp_bh);
	if (fatal)
		goto out;

	ret_block = grp_alloc_blk + ext3_group_first_block_no(sb, group_no);

	if (in_range(le32_to_cpu(gdp->bg_block_bitmap), ret_block, num) ||
	    in_range(le32_to_cpu(gdp->bg_inode_bitmap), ret_block, num) ||
	    in_range(ret_block, le32_to_cpu(gdp->bg_inode_table),
		      EXT3_SB(sb)->s_itb_per_group) ||
	    in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table),
		      EXT3_SB(sb)->s_itb_per_group)) {
		ext3_error(sb, "ext3_new_block",
			    "Allocating block in system zone - "
			    "blocks from "E3FSBLK", length %lu",
			     ret_block, num);
		/*
		 * claim_block() marked the blocks we allocated as in use. So we
		 * may want to selectively mark some of the blocks as free.
		 */
		goto retry_alloc;
	}

	performed_allocation = 1;

#ifdef CONFIG_JBD_DEBUG
	{
		struct buffer_head *debug_bh;

		/* Record bitmap buffer state in the newly allocated block */
		debug_bh = sb_find_get_block(sb, ret_block);
		if (debug_bh) {
			BUFFER_TRACE(debug_bh, "state when allocated");
			BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap state");
			brelse(debug_bh);
		}
	}
	jbd_lock_bh_state(bitmap_bh);
	spin_lock(sb_bgl_lock(sbi, group_no));
	if (buffer_jbd(bitmap_bh) && bh2jh(bitmap_bh)->b_committed_data) {
		int i;

		for (i = 0; i < num; i++) {
			if (ext3_test_bit(grp_alloc_blk+i,
					bh2jh(bitmap_bh)->b_committed_data)) {
				printk("%s: block was unexpectedly set in "
					"b_committed_data\n", __func__);
			}
		}
	}
	ext3_debug("found bit %d\n", grp_alloc_blk);
	spin_unlock(sb_bgl_lock(sbi, group_no));
	jbd_unlock_bh_state(bitmap_bh);
#endif

	if (ret_block + num - 1 >= le32_to_cpu(es->s_blocks_count)) {
		ext3_error(sb, "ext3_new_block",
			    "block("E3FSBLK") >= blocks count(%d) - "
			    "block_group = %d, es == %p ", ret_block,
			le32_to_cpu(es->s_blocks_count), group_no, es);
		goto out;
	}

	/*
	 * It is up to the caller to add the new buffer to a journal
	 * list of some description.  We don't know in advance whether
	 * the caller wants to use it as metadata or data.
	 */
	ext3_debug("allocating block %lu. Goal hits %d of %d.\n",
			ret_block, goal_hits, goal_attempts);

	spin_lock(sb_bgl_lock(sbi, group_no));
	le16_add_cpu(&gdp->bg_free_blocks_count, -num);
	spin_unlock(sb_bgl_lock(sbi, group_no));
	percpu_counter_sub(&sbi->s_freeblocks_counter, num);

	BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
	err = ext3_journal_dirty_metadata(handle, gdp_bh);
	if (!fatal)
		fatal = err;

	if (fatal)
		goto out;

	*errp = 0;
	brelse(bitmap_bh);

	if (num < *count) {
		dquot_free_block(inode, *count-num);
		*count = num;
	}

	trace_ext3_allocate_blocks(inode, goal, num,
				   (unsigned long long)ret_block);

	return ret_block;

io_error:
	*errp = -EIO;
out:
	if (fatal) {
		*errp = fatal;
		ext3_std_error(sb, fatal);
	}
	/*
	 * Undo the block allocation
	 */
	if (!performed_allocation)
		dquot_free_block(inode, *count);
	brelse(bitmap_bh);
	return 0;
}

ext3_fsblk_t ext3_new_block(handle_t *handle, struct inode *inode,
			ext3_fsblk_t goal, int *errp)
{
	unsigned long count = 1;

	return ext3_new_blocks(handle, inode, goal, &count, errp);
}

/**
 * ext3_count_free_blocks() -- count filesystem free blocks
 * @sb:		superblock
 *
 * Adds up the number of free blocks from each block group.
 */
ext3_fsblk_t ext3_count_free_blocks(struct super_block *sb)
{
	ext3_fsblk_t desc_count;
	struct ext3_group_desc *gdp;
	int i;
	unsigned long ngroups = EXT3_SB(sb)->s_groups_count;
#ifdef EXT3FS_DEBUG
	struct ext3_super_block *es;
	ext3_fsblk_t bitmap_count;
	unsigned long x;
	struct buffer_head *bitmap_bh = NULL;

	es = EXT3_SB(sb)->s_es;
	desc_count = 0;
	bitmap_count = 0;
	gdp = NULL;

	smp_rmb();
	for (i = 0; i < ngroups; i++) {
		gdp = ext3_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
		brelse(bitmap_bh);
		bitmap_bh = read_block_bitmap(sb, i);
		if (bitmap_bh == NULL)
			continue;

		x = ext3_count_free(bitmap_bh, sb->s_blocksize);
		printk("group %d: stored = %d, counted = %lu\n",
			i, le16_to_cpu(gdp->bg_free_blocks_count), x);
		bitmap_count += x;
	}
	brelse(bitmap_bh);
	printk("ext3_count_free_blocks: stored = "E3FSBLK
		", computed = "E3FSBLK", "E3FSBLK"\n",
	       le32_to_cpu(es->s_free_blocks_count),
		desc_count, bitmap_count);
	return bitmap_count;
#else
	desc_count = 0;
	smp_rmb();
	for (i = 0; i < ngroups; i++) {
		gdp = ext3_get_group_desc(sb, i, NULL);
		if (!gdp)
			continue;
		desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
	}

	return desc_count;
#endif
}

static inline int test_root(int a, int b)
{
	int num = b;

	while (a > num)
		num *= b;
	return num == a;
}

static int ext3_group_sparse(int group)
{
	if (group <= 1)
		return 1;
	if (!(group & 1))
		return 0;
	return (test_root(group, 7) || test_root(group, 5) ||
		test_root(group, 3));
}

/**
 *	ext3_bg_has_super - number of blocks used by the superblock in group
 *	@sb: superblock for filesystem
 *	@group: group number to check
 *
 *	Return the number of blocks used by the superblock (primary or backup)
 *	in this group.  Currently this will be only 0 or 1.
 */
int ext3_bg_has_super(struct super_block *sb, int group)
{
	if (EXT3_HAS_RO_COMPAT_FEATURE(sb,
				EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
			!ext3_group_sparse(group))
		return 0;
	return 1;
}

static unsigned long ext3_bg_num_gdb_meta(struct super_block *sb, int group)
{
	unsigned long metagroup = group / EXT3_DESC_PER_BLOCK(sb);
	unsigned long first = metagroup * EXT3_DESC_PER_BLOCK(sb);
	unsigned long last = first + EXT3_DESC_PER_BLOCK(sb) - 1;

	if (group == first || group == first + 1 || group == last)
		return 1;
	return 0;
}

static unsigned long ext3_bg_num_gdb_nometa(struct super_block *sb, int group)
{
	return ext3_bg_has_super(sb, group) ? EXT3_SB(sb)->s_gdb_count : 0;
}

/**
 *	ext3_bg_num_gdb - number of blocks used by the group table in group
 *	@sb: superblock for filesystem
 *	@group: group number to check
 *
 *	Return the number of blocks used by the group descriptor table
 *	(primary or backup) in this group.  In the future there may be a
 *	different number of descriptor blocks in each group.
 */
unsigned long ext3_bg_num_gdb(struct super_block *sb, int group)
{
	unsigned long first_meta_bg =
			le32_to_cpu(EXT3_SB(sb)->s_es->s_first_meta_bg);
	unsigned long metagroup = group / EXT3_DESC_PER_BLOCK(sb);

	if (!EXT3_HAS_INCOMPAT_FEATURE(sb,EXT3_FEATURE_INCOMPAT_META_BG) ||
			metagroup < first_meta_bg)
		return ext3_bg_num_gdb_nometa(sb,group);

	return ext3_bg_num_gdb_meta(sb,group);

}

/**
 * ext3_trim_all_free -- function to trim all free space in alloc. group
 * @sb:			super block for file system
 * @group:		allocation group to trim
 * @start:		first group block to examine
 * @max:		last group block to examine
 * @gdp:		allocation group description structure
 * @minblocks:		minimum extent block count
 *
 * ext3_trim_all_free walks through group's block bitmap searching for free
 * blocks. When the free block is found, it tries to allocate this block and
 * consequent free block to get the biggest free extent possible, until it
 * reaches any used block. Then issue a TRIM command on this extent and free
 * the extent in the block bitmap. This is done until whole group is scanned.
 */
static ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
					unsigned int group,
					ext3_grpblk_t start, ext3_grpblk_t max,
					ext3_grpblk_t minblocks)
{
	handle_t *handle;
	ext3_grpblk_t next, free_blocks, bit, freed, count = 0;
	ext3_fsblk_t discard_block;
	struct ext3_sb_info *sbi;
	struct buffer_head *gdp_bh, *bitmap_bh = NULL;
	struct ext3_group_desc *gdp;
	int err = 0, ret = 0;

	/*
	 * We will update one block bitmap, and one group descriptor
	 */
	handle = ext3_journal_start_sb(sb, 2);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	bitmap_bh = read_block_bitmap(sb, group);
	if (!bitmap_bh) {
		err = -EIO;
		goto err_out;
	}

	BUFFER_TRACE(bitmap_bh, "getting undo access");
	err = ext3_journal_get_undo_access(handle, bitmap_bh);
	if (err)
		goto err_out;

	gdp = ext3_get_group_desc(sb, group, &gdp_bh);
	if (!gdp) {
		err = -EIO;
		goto err_out;
	}

	BUFFER_TRACE(gdp_bh, "get_write_access");
	err = ext3_journal_get_write_access(handle, gdp_bh);
	if (err)
		goto err_out;

	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
	sbi = EXT3_SB(sb);

	 /* Walk through the whole group */
	while (start <= max) {
		start = bitmap_search_next_usable_block(start, bitmap_bh, max);
		if (start < 0)
			break;
		next = start;

		/*
		 * Allocate contiguous free extents by setting bits in the
		 * block bitmap
		 */
		while (next <= max
			&& claim_block(sb_bgl_lock(sbi, group),
					next, bitmap_bh)) {
			next++;
		}

		 /* We did not claim any blocks */
		if (next == start)
			continue;

		discard_block = (ext3_fsblk_t)start +
				ext3_group_first_block_no(sb, group);

		/* Update counters */
		spin_lock(sb_bgl_lock(sbi, group));
		le16_add_cpu(&gdp->bg_free_blocks_count, start - next);
		spin_unlock(sb_bgl_lock(sbi, group));
		percpu_counter_sub(&sbi->s_freeblocks_counter, next - start);

		free_blocks -= next - start;
		/* Do not issue a TRIM on extents smaller than minblocks */
		if ((next - start) < minblocks)
			goto free_extent;

		trace_ext3_discard_blocks(sb, discard_block, next - start);
		 /* Send the TRIM command down to the device */
		err = sb_issue_discard(sb, discard_block, next - start,
				       GFP_NOFS, 0);
		count += (next - start);
free_extent:
		freed = 0;

		/*
		 * Clear bits in the bitmap
		 */
		for (bit = start; bit < next; bit++) {
			BUFFER_TRACE(bitmap_bh, "clear bit");
			if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, group),
						bit, bitmap_bh->b_data)) {
				ext3_error(sb, __func__,
					"bit already cleared for block "E3FSBLK,
					 (unsigned long)bit);
				BUFFER_TRACE(bitmap_bh, "bit already cleared");
			} else {
				freed++;
			}
		}

		/* Update couters */
		spin_lock(sb_bgl_lock(sbi, group));
		le16_add_cpu(&gdp->bg_free_blocks_count, freed);
		spin_unlock(sb_bgl_lock(sbi, group));
		percpu_counter_add(&sbi->s_freeblocks_counter, freed);

		start = next;
		if (err < 0) {
			if (err != -EOPNOTSUPP)
				ext3_warning(sb, __func__, "Discard command "
					     "returned error %d\n", err);
			break;
		}

		if (fatal_signal_pending(current)) {
			err = -ERESTARTSYS;
			break;
		}

		cond_resched();

		/* No more suitable extents */
		if (free_blocks < minblocks)
			break;
	}

	/* We dirtied the bitmap block */
	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
	ret = ext3_journal_dirty_metadata(handle, bitmap_bh);
	if (!err)
		err = ret;

	/* And the group descriptor block */
	BUFFER_TRACE(gdp_bh, "dirtied group descriptor block");
	ret = ext3_journal_dirty_metadata(handle, gdp_bh);
	if (!err)
		err = ret;

	ext3_debug("trimmed %d blocks in the group %d\n",
		count, group);

err_out:
	if (err)
		count = err;
	ext3_journal_stop(handle);
	brelse(bitmap_bh);

	return count;
}

/**
 * ext3_trim_fs() -- trim ioctl handle function
 * @sb:			superblock for filesystem
 * @start:		First Byte to trim
 * @len:		number of Bytes to trim from start
 * @minlen:		minimum extent length in Bytes
 *
 * ext3_trim_fs goes through all allocation groups containing Bytes from
 * start to start+len. For each such a group ext3_trim_all_free function
 * is invoked to trim all free space.
 */
int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range)
{
	ext3_grpblk_t last_block, first_block;
	unsigned long group, first_group, last_group;
	struct ext3_group_desc *gdp;
	struct ext3_super_block *es = EXT3_SB(sb)->s_es;
	uint64_t start, minlen, end, trimmed = 0;
	ext3_fsblk_t first_data_blk =
			le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block);
	ext3_fsblk_t max_blks = le32_to_cpu(es->s_blocks_count);
	int ret = 0;

	start = range->start >> sb->s_blocksize_bits;
	end = start + (range->len >> sb->s_blocksize_bits) - 1;
	minlen = range->minlen >> sb->s_blocksize_bits;

	if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) ||
	    unlikely(start >= max_blks))
		return -EINVAL;
	if (end >= max_blks)
		end = max_blks - 1;
	if (end <= first_data_blk)
		goto out;
	if (start < first_data_blk)
		start = first_data_blk;

	smp_rmb();

	/* Determine first and last group to examine based on start and len */
	ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) start,
				     &first_group, &first_block);
	ext3_get_group_no_and_offset(sb, (ext3_fsblk_t) end,
				     &last_group, &last_block);

	/* end now represents the last block to discard in this group */
	end = EXT3_BLOCKS_PER_GROUP(sb) - 1;

	for (group = first_group; group <= last_group; group++) {
		gdp = ext3_get_group_desc(sb, group, NULL);
		if (!gdp)
			break;

		/*
		 * For all the groups except the last one, last block will
		 * always be EXT3_BLOCKS_PER_GROUP(sb)-1, so we only need to
		 * change it for the last group, note that last_block is
		 * already computed earlier by ext3_get_group_no_and_offset()
		 */
		if (group == last_group)
			end = last_block;

		if (le16_to_cpu(gdp->bg_free_blocks_count) >= minlen) {
			ret = ext3_trim_all_free(sb, group, first_block,
						 end, minlen);
			if (ret < 0)
				break;
			trimmed += ret;
		}

		/*
		 * For every group except the first one, we are sure
		 * that the first block to discard will be block #0.
		 */
		first_block = 0;
	}

	if (ret > 0)
		ret = 0;

out:
	range->len = trimmed * sb->s_blocksize;
	return ret;
}
OpenPOWER on IntegriCloud